Normalization of the dataset, Error: all elements of input should be between 0 and 1

Question

当我尝试执行训练时，PyTorch 中的数据规范化出现问题。首先你需要知道的是，数据集由 3024 个信号 windows（所以 1 个通道）组成，每个信号的长度为 5000 个样本，因此 CSV 文件的尺寸为 5000x3024。每个信号都有 1 个需要预测的标签。这是我如何加载和规范化数据的代码：

class CSVDataset(Dataset):
    # load the dataset
    def __init__(self, path, normalize = False):
        # load the csv file as a dataframe
        df = read_csv(path)
        df = df.transpose()
        # store the inputs and outputs
        self.X = df.values[:, :-1]
        self.y = df.values[:, -1]
        print("Dataset length: ", self.X.shape[0])
        # ensure input data is floats
        self.X = self.X.astype(np.float)
        self.y = self.y.astype(np.float)
        
        if normalize:
            self.X = self.X.reshape(self.X.shape[1], self.X.shape[0])
            min_X = np.min(self.X,0)  # returns an array of means for each signal window
            max_X = np.max(self.X,0)
            self.X = (self.X - min_X)/(max_X-min_X)
            min_y = np.min(self.y) 
            max_y = np.max(self.y)
            self.y = (self.y - min_y)/(max_y-min_y)
        
        # reshape input data
        self.X = self.X.reshape(self.X.shape[0], 1, self.X.shape[1])
        self.y = self.y.reshape(self.y.shape[0], 1)
        # label encode target and ensure the values are floats
        self.y = LabelEncoder().fit_transform(self.y)
        self.y = self.y.astype(np.float)

# prepare the dataset
def prepare_data(path):
    # load the dataset
    dataset = CSVDataset(path, normalize = True)
    # calculate split
    train, test = dataset.get_splits()
    # prepare data loaders
    train_dl = DataLoader(train, batch_size=32, shuffle=True)
    test_dl = DataLoader(test, batch_size=1024, shuffle=False)
    return train_dl, test_dl

而训练方法是：

def train_model(train_dl, model):
    # define the optimization
    criterion = BCELoss()
    optimizer = SGD(model.parameters(), lr=0.01, momentum=0.9)
    model = model.float()
    # enumerate epochs
    for epoch in range(100):
        # enumerate mini batches
        for i, (inputs, targets) in enumerate(iter(train_dl)):
            targets = torch.reshape(targets, (32, 1))
            # clear the gradients
            optimizer.zero_grad()
            # compute the model output
            yhat = model(inputs.float())
            # calculate loss
            loss = criterion(yhat, targets.float())
            # credit assignment
            loss.backward()
            # update model weights
            optimizer.step()

我得到的错误在行 loss = criterion(yhat, targets.float()) 中，它说：

RuntimeError: all elements of input should be between 0 and 1

我已经尝试检查变量资源管理器中的 X，似乎没有任何值不在 0 和 1 之间。我不知道我在规范化中可能做错了什么。你能帮帮我吗？

Answer 1

内置损失函数参考输入和目标指定预测和label 个实例。错误消息应理解为“标准的输入”即 yhat，而不是“模型的输入”。

似乎 yhat 不属于 [0, 1]，而 BCELoss 期望的是概率，而不是对数。你可以

添加一个 sigmoid 层作为模型的最后一层，或者
改用 nn.BCEWithLogitsLoss，它结合了 sigmoid 和 bce 损失。

Normalization of the dataset, Error: all elements of input should be between 0 and 1

Normalization of the dataset, Error: all elements of input should be between 0 and 1

neural-network

deep-learning

pytorch